HR Assistant Agent
Answers leave, benefits, and policy questions in Slack straight from your Notion handbook, links the page it read, and hands anything personal to a human.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
How much parental leave do I get?
Priya Raghavan
@hr our baby is due on 14 March, how much parental leave do I get and is any of it paid? Also is there a date I have to tell my manager by?
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Notion
One sign-in. The agent acts through your account, scoped to what this template uses.
Company name
Your company name as your team says it in Slack, so the assistant sounds like it works there.
Policy notes
Where your policies live in Notion, page or database by page, covering leave, benefits, expenses, and working hours, plus any rule your team follows that nobody has written down yet. The assistant only ever answers from what you list here.
Hr contact
Who takes what a document cannot answer, written exactly as you want it said in Slack: a person's handle, an HR channel, or an email. If different people cover different things, say which is which.
Choose which agent runs it
NoClick's built-in models work out of the box — or bring Claude Code, Codex, and other coding agents on your own subscription.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
About this agent
Your HR lead answers the same eight questions every week, and each one lands as a DM at the worst possible moment. This assistant sits in Slack, answers policy questions from the Notion pages you point it at, and always links the page it read so nobody has to take its word for it. Anything about a specific person, their pay, a complaint, a contract, their health, it refuses on purpose and sends them to a human.
What people use it for
- Kill the repeat HR questions - Holiday rules, notice periods, expense limits, and benefits questions get answered in thread the moment they are asked. That is most of an HR inbox, handled without anyone being interrupted.
- Onboarding without hand-holding - New joiners ask the assistant instead of guessing or interrupting their manager, and get the same answer off the same handbook page every time.
- Leave and remote work requests - Questions about sick leave, working from another country, or notice periods are answered from your written process, so people follow it instead of inventing their own version.
- Find the gaps in your handbook - Every answer cites the page it came from, so a wrong answer points straight at the page that needs fixing, and every refusal tells you a policy you have never written down.
Before you fork
What does it need connected?
Slack, so it can be mentioned and reply in thread, and Notion, so it can read your policies. It only reads Notion, it cannot create or edit pages. You name the pages or databases it may use, and it does not wander outside them.
Could it leak someone's private information?
Two things stop it. Keep individual records, salary bands, and performance docs out of the Notion space you point it at, so the data is simply not reachable. On top of that its instructions refuse every personal question outright, including pay, complaints, contracts, and anything medical, and route the person to your HR contact instead of answering.
What happens when the handbook does not cover something?
It says so, tells the person what it checked, and names your HR contact. It never fills a gap with what is normal at other companies, which is the failure mode that makes an HR bot genuinely dangerous. Those refusals are also the best list you will get of what to write down next.
Run it with your coding agent
More agents like this
Put HR Assistant Agent to work
Free to start. Guided setup, a test run against staged conversations, and it's live.